Fast single image super-resolution using estimated low-frequency k-space data in MRI

Luo, Jianhua; Mou, Zhiying; Qin, Binjie; Li, Wanqing; Yang, Feng; Robini, Marc; Zhu, Yuemin

doi:10.1016/j.mri.2017.03.008

Cited by 13 publications

(15 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first application of SR in MRI was proposed by Peled et al, where multiples of spatially shifted, single‐shot, diffusion‐weighted brain images were fused to generate a new image with improved resolution and finer detail . Since then, various advanced SR techniques established in MRI have offered the possibility to efficiently improve the image resolution and increase the diagnostic potential …”

Section: Introductionmentioning

confidence: 99%

“…There are generally three methods to achieve image SR in MRI: (a) interpolation‐based, (b) reconstruction‐based, and (c) machine learning‐based . Interpolation‐based techniques assume that points/regions in an LR image can be expanded into corresponding points/regions in the SR reconstruction using polynomial or interpolation functions with some smoothness priors, which is not valid in inhomogeneous regions . Moreover, the actual LR sampled points represent a nonideal sampling where the sampled points represent the intermediate value of the underlying HR points that exist within the LR points.…”

Section: Introductionmentioning

confidence: 99%

“…The reconstruction‐based SR methods solve an optimization problem incorporating two terms: the fidelity term, which penalizes the difference between a degraded SR image and an observed LR image, and the regularization term, which promotes sparsity and inherent characteristics of recovering the SR signal (e.g., edge gradient). However, the performance of these techniques becomes suboptimal especially in the high‐frequency region when the input data becomes too sparse or the model becomes even slightly inaccurate . Such drawbacks limit the effectiveness of these methods to small magnification factors that are less than 4.…”

Section: Introductionmentioning

confidence: 99%

“…20 Since then, various advanced SR techniques established in MRI have offered the possibility to efficiently improve the image resolution and increase the diagnostic potential. 2,18,[21][22][23][24][25] There are generally three methods to achieve image SR in MRI: (a) interpolation-based 9,26,27 , (b) reconstructionbased [28][29][30] , and (c) machine learning-based. [31][32][33][34][35] Interpolation-based techniques assume that points/regions in an LR image can be expanded into corresponding points/regions in the SR reconstruction using polynomial or interpolation functions with some smoothness priors, 9,26,27 which is not valid in inhomogeneous regions.…”

Section: Introductionmentioning

confidence: 99%

“…[31][32][33][34][35] Interpolation-based techniques assume that points/regions in an LR image can be expanded into corresponding points/regions in the SR reconstruction using polynomial or interpolation functions with some smoothness priors, 9,26,27 which is not valid in inhomogeneous regions. 25 Moreover, the actual LR sampled points represent a nonideal sampling where the sampled points represent the intermediate value of the underlying HR points that exist within the LR points. Hence, SR through interpolation results in a blurred version of the corresponding HR reference images.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

MRI super‐resolution reconstruction for MRI‐guided adaptive radiotherapy using cascaded deep learning: In the presence of limited training data and unknown translation model

et al. 2019

View full text Add to dashboard Cite

Purpose Deep learning (DL)‐based super‐resolution (SR) reconstruction for magnetic resonance imaging (MRI) has recently been receiving attention due to the significant improvement in spatial resolution compared to conventional SR techniques. Challenges hindering the widespread implementation of these approaches remain, however. Low‐resolution (LR) MRIs captured in the clinic exhibit complex tissue structures obfuscated by noise that are difficult for a simple DL framework to handle. Moreover, training a robust network for a SR task requires abundant, perfectly matched pairs of LR and high‐resolution (HR) images that are often unavailable or difficult to collect. The purpose of this study is to develop a novel SR technique for MRI based on the concept of cascaded DL that allows for the reconstruction of high‐quality SR images in the presence of insufficient training data, an unknown translation model, and noise. Methods The proposed framework, based on the concept named cascaded deep learning, consists of three components: (a) a denoising autoencoder (DAE) trained using clinical LR noisy MRI scans that have been processed with a nonlocal means filter that generates denoised LR data; (b) a down‐sampling network (DSN) trained with a small amount of paired LR/HR data from volunteers that allows for the generation of perfectly paired LR/HR data for the training of a generative model; and (c) the proposed SR generative model (p‐SRG) trained with data generated by the DSN that maps from LR inputs to HR outputs. After training, LR clinical images may be fed through the DAE and p‐SRG to yield SR reconstructions of the LR input. The application of this framework was explored in two settings: 3D breath‐hold MRI axial SR reconstruction from LR axial scans (<3 sec/vol) and in the enhancement of the spatial resolution of LR 4D‐MRI acquisitions (0.5 sec/vol). Results The DSN produces LR scans from HR inputs with a higher fidelity to true, LR clinical scans compared to conventional k‐space down‐sampling methods based on the metrics of root mean square error (RMSE) and structural similarity index (SSIM). Furthermore, HR outputs generated by the p‐SRG exhibit improved scores in the peak signal‐to‐noise ratio, normalized RMSE, SSIM, and in the blind/reference‐less image spatial quality evaluator assessment compared to conventional approaches to MRI SR. Conclusions The robust, SR reconstruction method for MRI based on the novel cascaded deep learning framework is an end‐to‐end method for producing detail‐preserving SR reconstructions from noisy, LR clinical MRI scans. Fourfold enhancements in spatial resolution facilitate target delineation and motion management during radiation therapy, enabling precise MRI‐guided radiation therapy with 3D LR breath‐hold MRI and 4D‐MRI in a clinically feasible time frame.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

MRI super‐resolution reconstruction for MRI‐guided adaptive radiotherapy using cascaded deep learning: In the presence of limited training data and unknown translation model

et al. 2019

View full text Add to dashboard Cite

show abstract

Towards Super-resolution CEST MRI for Visualization of Small Structures

et al. 2022

View full text Add to dashboard Cite

FA-GAN: Fused attentive generative adversarial networks for MRI image super-resolution

Jiang

Zhi

Wei

et al. 2021

Computerized Medical Imaging and Graphics

View full text Add to dashboard Cite

Highlights A fused attentive generative adversarial networks framework is proposed for MR image super-resolution. A combination of channel attention and self-attention is used to calculate the weight parameters of the input features. Spectral normalization process is introduced to make the discriminator network stabler. The proposed FA-GAN method is superior to the state-of-the-art reconstruction methods.

show abstract

Fast single image super-resolution using estimated low-frequency k-space data in MRI

Cited by 13 publications

References 33 publications

MRI super‐resolution reconstruction for MRI‐guided adaptive radiotherapy using cascaded deep learning: In the presence of limited training data and unknown translation model

MRI super‐resolution reconstruction for MRI‐guided adaptive radiotherapy using cascaded deep learning: In the presence of limited training data and unknown translation model

Towards Super-resolution CEST MRI for Visualization of Small Structures

FA-GAN: Fused attentive generative adversarial networks for MRI image super-resolution

Contact Info

Product

Resources

About